Research map / Detection and segmentation / CNN features
Gradient-Induced Co-Saliency Detection
Zhao Zhang, Wenda Jin, Jun Xu, Ming-Ming Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add GIM to the baseline (ablation) | SOD baseline · CoCA | F_avg: 0.420 -> 0.446 | Improved |
| add ARM to the baseline without GIM (ablation) | SOD baseline · CoCA | F_avg: 0.420 -> 0.429 | No clear effect |
| add ARM to GIM (ablation) | GICD without JT · CoCA | F_avg: 0.446 -> 0.471 | Improved |
| add ARM to JT + GIM (full model) (ablation) | GICD · CoCA | F_avg: 0.470 -> 0.504 | Improved |
| add JT to GIM + ARM (full model) (ablation) | GICD · CoCA | F_avg: 0.471 -> 0.504 | Improved |
| add JT to GIM (ablation) | GICD without ARM · CoCA | F_avg: 0.446 -> 0.470 | Improved |
| add JT without GIM (ablation) | SOD baseline · CoSal2015 | F_avg: 0.788 -> 0.750 | Hurt |
| add JT without GIM (ablation) | SOD baseline · CoCA | F_avg: 0.420 -> 0.424 | No clear effect |
| add JT to GIM + ARM (full model) (ablation) | GICD · CoSal2015 | F_avg: 0.826 -> 0.835 | Improved |
| add JT to GIM (ablation) | GICD without ARM · CoSal2015 | F_avg: 0.809 -> 0.795 | Hurt |
| use GICD instead of best Co-SOD method | co-saliency detection · CoSal2015 | F_avg: 11.4% improvement | Improved |
| use GICD instead of best SOD method | co-saliency detection · CoSal2015 | F_avg: 5.7% improvement | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BASNet — BASNet: Boundary-Aware Salient Object Detection (CVPR 2019) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Detection of Co-salient Objects by Looking Deep and Wide (IJCV 2016 · similarity 0.91)
- ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020 · similarity 0.91)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.90)
- Unsupervised CNN-based Co-Saliency Detection with Graphical Optimization (ECCV 2018 · similarity 0.90)
- Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (TPAMI 2016 · similarity 0.90)
- Robust Deep Co-Saliency Detection with Group Semantic (AAAI 2019 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
